A$^2$TG: Adaptive Anisotropic Textured Gaussians for Efficient 3D Scene Representation
This work addresses memory efficiency for 3D rendering applications, representing an incremental improvement over existing Gaussian splatting methods.
The paper tackled the problem of inefficient memory usage in textured Gaussian splatting for 3D scene representation by introducing adaptive anisotropic textured Gaussians (A^2TG), which reduced memory consumption while maintaining comparable rendering fidelity.
Gaussian Splatting has emerged as a powerful representation for high-quality, real-time 3D scene rendering. While recent works extend Gaussians with learnable textures to enrich visual appearance, existing approaches allocate a fixed square texture per primitive, leading to inefficient memory usage and limited adaptability to scene variability. In this paper, we introduce adaptive anisotropic textured Gaussians (A$^2$TG), a novel representation that generalizes textured Gaussians by equipping each primitive with an anisotropic texture. Our method employs a gradient-guided adaptive rule to jointly determine texture resolution and aspect ratio, enabling non-uniform, detail-aware allocation that aligns with the anisotropic nature of Gaussian splats. This design significantly improves texture efficiency, reducing memory consumption while enhancing image quality. Experiments on multiple benchmark datasets demonstrate that A TG consistently outperforms fixed-texture Gaussian Splatting methods, achieving comparable rendering fidelity with substantially lower memory requirements.